Publication

SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation

European Conference on Computer Vision (ECCV)


Abstract

LiDAR point-cloud segmentation is an important problem for many applications. For large-scale point cloud segmentation, the de facto method is to project a 3D point cloud to get a 2D LiDAR image and use convolutions to process it. Despite the similarity between regular RGB and LiDAR images, we are the first to discover that the feature distribution of LiDAR images changes drastically at different image locations. Using standard convolutions to process such LiDAR images is problematic, as convolution filters pick up local features that are only active in specific regions in the image. As a result, the capacity of the network is under-utilized and the segmentation performance decreases. To fix this, we propose Spatially-Adaptive Convolution (SAC) to adopt different filters for different locations according to the input image. SAC can be computed efficiently since it can be implemented as a series of element-wise multiplications, im2col, and standard convolution. It is a general framework such that several previous methods can be seen as special cases of SAC. Using SAC, we build SqueezeSegV3 for LiDAR point-cloud segmentation and outperform all previous published methods by at least 2.0% mIoU on the SemanticKITTI benchmark. Code and pretrained model are available at https://github.com/chenfengxu714/SqueezeSegV3.

Related Publications

All Publications

Design Automation Conference (DAC) - December 5, 2021

F-CAD: A Framework to Explore Hardware Accelerators for Codec Avatar Decoding

Xiaofan Zhang, Dawei Wang, Pierce Chuang, Shugao Ma, Deming Chen, Yuecheng Li

NeurIPS - December 5, 2021

Interpretable agent communication from scratch (with a generic visual processor emerging on the side)

Roberto Dessì, Eugene Kharitonov, Marco Baroni

IEEE Transactions on Haptics (ToH) - January 1, 2022

Data-driven sparse skin stimulation can convey social touch information to humans

Mike Salvato, Sophia R. Williams, Cara M. Nunez, Xin Zhu, Ali Israr, Frances Lau, Keith Klumb, Freddy Abnousi, Allison M. Okamura, Heather Culbertson

ECCV - August 24, 2020

Geometric Correspondence Fields: Learned Differentiable Rendering for 3D Pose Refinement in the Wild

Alexander Grabner, Yaming Wang, Peizhao Zhang, Peihong Guo, Tong Xiao, Peter Vajda, Peter M. Roth, Vincent Lepetit

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookie Policy